Related papers: Bridging the inference gap in Mutimodal Variationa…

Ensemble weather forecasts based on multiple runs of numerical weather prediction models typically show systematic errors and require post-processing to obtain reliable forecasts. Accurately modeling multivariate dependencies is crucial in…

Multimodal representation learning has demonstrated remarkable potential in enabling models to process and integrate diverse data modalities, such as text and images, for improved understanding and performance. While the medical domain can…

This paper presents a novel approach for learning self-awareness models for autonomous vehicles. The proposed technique is based on the availability of synchronized multi-sensor dynamic data related to different maneuvering tasks performed…

Multimodal Variational Autoencoders (VAEs) have been the subject of intense research in the past years as they can integrate multiple modalities into a joint representation and can thus serve as a promising tool for both data classification…

In this paper, we propose an end-to-end lifelong learning mixture of experts. Each expert is implemented by a Variational Autoencoder (VAE). The experts in the mixture system are jointly trained by maximizing a mixture of individual…

Prevalent in biomedical applications (e.g., human phenotype research), multimodal datasets can provide valuable insights into the underlying physiological mechanisms. However, current machine learning (ML) models designed to analyze these…

Multimodal federated learning holds immense potential for collaboratively training models from multiple sources without sharing raw data, addressing both data scarcity and privacy concerns, two key challenges in healthcare. A major…

Variational Autoencoders (VAEs) are a popular generative model, but one in which conditional inference can be challenging. If the decomposition into query and evidence variables is fixed, conditional VAEs provide an attractive solution. To…

Simultaneously using multimodal inputs from multiple sensors to train segmentors is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where multimodal segmentors over rely on certain modalities, causing…

This paper proposes a method for performing continual learning of predictive models that facilitate the inference of future frames in video sequences. For a first given experience, an initial Variational Autoencoder, together with a set of…

Future prediction is a fundamental principle of intelligence that helps plan actions and avoid possible dangers. As the future is uncertain to a large extent, modeling the uncertainty and multimodality of the future states is of great…

We describe and analyze a broad class of mixture models for real-valued multivariate data in which the probability density of observations within each component of the model is represented as an arbitrary combination of basis functions.…

Probability density function estimation with weighted samples is the main foundation of all adaptive importance sampling algorithms. Classically, a target distribution is approximated either by a non-parametric model or within a parametric…

The development of high-dimensional generative models has recently gained a great surge of interest with the introduction of variational auto-encoders and generative adversarial neural networks. Different variants have been proposed where…

This work studies the problem of modeling visual processes by leveraging deep generative architectures for learning linear, Gaussian representations from observed sequences. We propose a joint learning framework, combining a vector…

The commonly used latent space embedding techniques, such as Principal Component Analysis, Factor Analysis, and manifold learning techniques, are typically used for learning effective representations of homogeneous data. However, they do…

Inferring causal effects of a treatment, intervention or policy from observational data is central to many applications. However, state-of-the-art methods for causal inference seldom consider the possibility that covariates have missing…

Continuously-observed event occurrences, often exhibit self- and mutually-exciting effects, which can be well modeled using temporal point processes. Beyond that, these event dynamics may also change over time, with certain periodic trends.…

Condition monitoring of industrial systems is crucial for ensuring safety and maintenance planning, yet notable challenges arise in real-world settings due to the limited or non-existent availability of fault samples. This paper introduces…

We introduce physics-informed multimodal autoencoders (PIMA) - a variational inference framework for discovering shared information in multimodal scientific datasets representative of high-throughput testing. Individual modalities are…